Ismael Faro

Future of #Art 👨‍🎨 ? Only with Immersive Tech! This amazing audio-visual exposition combines camera inputs, programmable LED, and spatial audio and creates a mesmerizing show. I love the transition between full image and LED strips. Let's connect and explore the Immersive World together with YORD! Credit: Ksawery Kirklewski & team This post is part of the Future of Immersive Tech series. Check out my profile & 🔔 for more! Always happy for 🔁 , 💬 or 👍 ! #interactive #futuretech

124

8 Comments

Raspberry Pi 5 is getting a first party AI accelerator add on, Hailo 8L accelerator which can do 13 trillion operations at int8 , enough to run quantized LLM's fast, processing videos in real time What would you build if you get access to it?

33

2 Comments

Designing for New Realities in the Age of Spatial Computing + AI https://lnkd.in/e6XJhRUe via Bezi In the dynamic intersection of #spatialcomputing and #AI, today’s futuristic technologies are reshaping our digital interactions. As these ways of computing converge, new considerations are emerging for how we build for the world around us. Key takeaways on how to design for these new realities: ⇒ Is spatial computing ready for mass consumers? ⇒ How do major tech investments influence universal design standards? ⇒ How will real-time personalized products impact the spatial computing industry? ⇒ How are design roles evolving in an era of individually tailored UI experiences? ⇒ How can designers create safe spatial computing environments? ⇒ How can designers develop innovative input paradigms for spatial computing? ⇒ How can designers prioritize digital ethics in spatial computing? "We are all in the process together right now of setting these standards and we have to hold human needs as the highest order problem." — Michelle Cortese, Meta XR Design Lead "Spatial computing is really anything that uses the physical context of the world that surrounds you — there's been this gradual emergence of these technologies which have this characteristic of bringing in more of your context and being able to use that in a computation." — Keiichi Matsuda, Founder of Liquid City "There's so much opportunity here to make more malleable, more personal #software where it adapts itself — based on what your needs are. Systems that reposition themselves according to an individual's needs will help people feel connected to technology rather than feeling forced to adapt it”.  — Agatha Yu, Human Interface Designer Manager

21

1 Comment

#GenAI #fashion #3d #tools #creativity great progress in the field : rendering, shapes and the fold, textiles realism, remains a challenge that AI can solve shortly

5

1 Comment

Want to understand how the Meta Orion and Snapchat spectacles prototypes of AR glasses compare ? Look at this excellent video from Marques Brownlee https://lnkd.in/eWEiWSNs Want to update your vocabulary when speaking of immersive devices and how they give you or not a sense of presence ? Read the comment I made on the video and copied below 👇 (Referring Mel Slater) —- Hi Marques, very interesting comparison, thank you You are wondering at minute 15 if you should use the word immersion to describe what happens to you when the lack of FOV cuts the overlay Let me point you to one of the most important scientific paper on the topic, a reference in the research community on VR (I’m part of it since almost 30 years): https://lnkd.in/eRGciSfz Besides immersion, the other useful words here are: presence, plausibility and illusion In short: - Immersion is a way to compare technical capacities of devices: the Meta glasses are more immersive in terms of FOV, the snap glasses are more immersive in terms of resolution … - Presence is what it makes to the user in terms of feeling, in its mind Presence is made of 2 factors: place illusion and plausibility illusion - Place illusion is the perceptual (scientists say “sensory-motor”) part: it is the sentiment of non mediation of the device, or the fact that you believe things are here - Plausibility illusion is more cognitive: it has to do with storytelling, consistency of the experience, absence of gliches over time. It depends more on the content of the experience and less on the container. Place illusion is easy to recover when it’s broken: when your overlay is being cut on the side it breaks the presence, but when recentered its presence is restored On the other hand, plausibility illusion is hard to restore when broken. Hope this helps ! Cheers David Nahon. @iVEvangelist

8

1 Comment

🪩🪩MimicMotion: HQ Motion Generation🪩🪩 👉#Tencent opens a novel controllable video generation framework, dubbed MimicMotion, which can generate HQ videos of arbitrary length mimicking specific motion guidance. Source Code available💙 𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬: ✅MimicMotion: I2V diffusion + confidence-aware pose ✅Rich details, good temporal smoothness & long video ✅Better pose by novel confidence-aware strategy ✅Correcting erroneous pose guidance during inference ✅Hand region enhancement to alleviate hand distortion ✅Position-aware progressive latent fusion #artificialintelligence #machinelearning #ml #AI #deeplearning #computervision #AIwithPapers #metaverse 👉Discussion https://lnkd.in/dMgakzWm 👉Paper arxiv.org/pdf/2406.19680 👉Project https://lnkd.in/eW-CMg_C 👉Code https://lnkd.in/eZ6SC2bc

231

Protecting artistic integrity Glaze 2 unveils enhanced anti-AI scraping capabilities The University of Chicago's Glaze Project team has launched an advanced version of their acclaimed anti-AI scraping tool, Glaze 2, significantly boosting the protection of artists' original works against unauthorized AI mimicry. Designed to disrupt AI models from emulating unique artistic styles, Glaze 2 introduces speed improvements and enhanced defenses, particularly against sophisticated models like Stable Diffusion XL. Since its initial release in 2023, Glaze has been a cornerstone for artists to shield their styles without altering the visual fidelity for human viewers. The latest iteration, Glaze 2, not only operates up to 500% faster on modern hardware but also increases its effectiveness against AI-driven style mimicry. This version promises stronger protection for diverse art forms, including smooth surface art like cartoons and anime, by introducing more disruptive artifacts that challenge AI's replication abilities. The impact of Glaze is evident, with over 2.3 million downloads, reflecting the growing concern among artists about digital identity theft and the dilution of their creative signatures. The Glaze Project team is also expanding their protective technology to video content, promising new avenues for artists to safeguard their multimedia expressions from AI exploitation. As digital and AI technologies evolve, tools like Glaze 2 are vital in ensuring that the creativity and rights of artists are preserved. This development not only enhances the toolkit available to artists but also sets a standard for ethical AI usage respecting artistic copyrights. #ArtTech #DigitalRights #AI #Glaze2 #responsibleai https://lnkd.in/gpaVmBZC

2

The Outernet #ImmersiveExperience FIRST AI ART DATA SPATIAL PAINTING "HUMAN CELL ATLAS_Neuroorganismic AI Data Spatial Painting of Humanity" by Ouchhh! #aiartdataspatial #immersivtech #aicontent #aiart #dataspatial #newmediaart #futuretech #ledscreens #artinstallations #immersive #artandtechnology #ai

100

10 Comments

💡💡DifFRelight: Diffusion Models Relighting💡💡 👉#Netflix (Eyeline Studios) unveils DifFRelight, a novel framework for free-viewpoint facial performance relighting via diffusion model. Precise lighting control, enabling high-fidelity relit facial images from flat-lit inputs. No code announced but amazing results. 𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬: ✅Free-viewpoint face relighting via diffusion ✅Spatially-aligned conditioning of flat-lit & noise ✅Unified control by integrating novel area lighting ✅HDRI composition via multiple directional lights #artificialintelligence #machinelearning #ml #AI #deeplearning #computervision #AIwithPapers #metaverse 👉Discussion https://lnkd.in/dMgakzWm 👉Paper arxiv.org/pdf/2410.08188 👉Project https://lnkd.in/dku5crPY

179

5 Comments

Chinese new DiT Video AI Generation model 【KLING】 Generate 120-second videos at 30 FPS in 1080P, with improved physics understanding and accurate modeling of complex motion. prompt: Traveling by train, viewing all sorts of landscapes through the window. https://lnkd.in/gWYRDfQ5 #DiTVideoAI #KLINGModel #AIAnimation #VideoGeneration #1080PVideo #AIInnovation

4

AI Democratization at scale ! Watched the CES NVIDIA keynote. Here's the breakdown of the announcements: 🤖 1️⃣ Project DIGITS & GB10 Superchip A 200B-parameter AI supercomputer in your palm. This isn't science fiction - it's happening now. The implications for edge AI are staggering. 2️⃣ Autonomous Mobility Revolution Cosmos World Foundation Models + three-computer solution = billions of virtual testing miles. Aurora and Continental are already deploying NVIDIA DRIVE-powered driverless trucks at scale. 3️⃣ DRIVE Thor Built on the Blackwell architecture, setting new benchmarks for autonomous vehicle safety and security. 4️⃣ Next-Gen Video AI Blueprint Chain-of-thought reasoning and dynamic task planning are transforming video search and summarization. The possibilities for content creators are endless. 5️⃣ 'Mega' Omniverse for Manufacturing Digital twin technology simulating entire robot fleets. This could revolutionize the $50T manufacturing and logistics industries. 6️⃣ Nemotron AI Models NVIDIA NIM microservices bringing enterprise-grade AI to any accelerated system through Llama Nemotron language models and Cosmos Nemotron vision models. 7️⃣ Omniverse Sensor RTX Early access announced! Foretellix's implementation shows how accurate sensor simulation is transforming autonomous system development. 8️⃣ RTX AI PC Evolution NIM microservices and AI Blueprints democratizing access to generative AI. Digital humans and content creation workflows are becoming plug-and-play. 🎯 The Showstopper: RTX 5070 promising RTX 4090 performance at just $549. High-end AI capabilities are becoming more accessible than ever. The convergence of more powerful, more accessible AI computing with sophisticated simulation capabilities suggests we're entering a new era of technological innovation. More competition on the way but what possibilities do we see with digital twin technology? #AI #Data #Innovation #gaming #CES2025 #NVIDIA

14